跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 07:46 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 07:49 — 2026-11-20 07:49(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 07:46最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

27,982 已收录论文23,249 AI 相关8,559 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,249 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 07:44(北京时间)
版本更新 · v2arXiv:2609.29140

Cost-Efficient LLM Evaluation: A Framework for Narrow Confidence Intervals Under Fixed Budgets

Yezhou Cheng, Runjia Du, Zeming Liu, Qibai Chen, Hang Lyu, Yilan Wei, Yankai Zeng, Bojun Lin

原文摘要

Large language models (LLMs) play an increasingly important role in both academic research and industry. Reliable evaluation helps researchers understand model capabilities and assess progress during model development. However, evaluation can be costly, and researchers often need to assess performance within a fixed budget. Because model outputs can vary across runs, this budget must be allocated between testing different tasks and repeating selected tasks. A confidence interval quantifies the uncertainty in the resulting performance estimate. Obtaining narrower intervals at the same confidence level and evaluation cost provides a more precise assessment of model performance, helping researchers draw clearer conclusions from limited observations. We introduce a framework that allocates a fixed evaluation budget across tasks and repeated runs, with or without full task coverage. The framework then uses disagreements between runs on the same task to bound estimation error, allowing narrower confidence intervals at the same confidence level when the sampled repeats show little variability. When repeated runs on each task yield the same outcome, we prove that our framework achieves the fastest theoretically possible rates for narrowing confidence intervals in the worst case as the number of tasks and the budget for repeats grow. We establish matching lower bounds both when every task must be covered and when tasks may be skipped, even for evaluators who use earlier results to decide which run to carry out next. On LiveCodeBench, our framework yielded narrower confidence intervals on average than uniform random sampling in 15 of 16 model configurations, with a median width reduction of 30.6% at the same confidence level and the same budget of 1,100 outputs per configuration.

cs.AI · cs.IT

版本更新 · v3arXiv:2605.28792

CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models

Abhilash Durgam, Nyle Siddiqui, Jeffrey A. Chan-Santiago, Qiushi Fu, Elakkat D. Gireesh, Mubarak Shah

原文摘要

Electroencephalography (EEG) is a critical, non-invasive method to monitor electrical brain activity. EEGs can span anywhere from a couple seconds to multiple hours, posing a major hurdle for existing deep learning methods due to two major factors: (1) existing EEG models are predominantly built upon the attention mechanism, incurring quadratic scaling as the sequence length increases, and (2) raw EEG signals must be processed in a sliding-window fashion due to fixed-length input requirements, preventing global understanding of the entire signal. To this extent, we propose CaMBRAIN - the first Causal, Mamba-based state space model (SSM) capable of real-time inference of EEG signals, arguing that bidirectional approaches are needlessly expensive given the causal, unidirectional nature of EEG. However, training such a model is non-trivial, as crucial EEG events can be extremely brief - within fractions of a second - yet separated by long intervals spanning minutes. Current EEG methods use self-supervised objectives that optimize for signal reconstruction, but these are not well suited for streaming SSMs; they fail to explicitly train the hidden state to retain the salient long-range context needed for streaming inference. We therefore introduce a multi-stage self-supervised training pipeline specifically tailored to encourage long-range memory retention and strong performance on EEG signals, while preserving the linear-time complexity of state space models. CaMBRAIN achieves state-of-the-art (SOTA) results across 3 different EEG datasets with >10x higher throughput than existing models, enabling the first model capable of long-range, continuous inference of variable-length EEG signals.

cs.AI · cs.HC · cs.LG

新论文 · v1arXiv:2611.23674

Learning What to Degrade: A Recoverability-Aware Curriculum for Reliable Smart-Glasses Super-Resolution

Yaopeng Wang, Qingliang Wang, Yilun Jin, Xiujin Liu, Han Yue, Chen Xia, Renjie Zhu, Chuang Sheng

原文摘要

Degradations in smart-glasses images obscure small text and fine-grained structures needed by vision-language models (VLMs) for visual assistance. We introduce an high-resolution (HR)-referenced semantic evaluation protocol that compares VLM outputs on restored images with those on corresponding HR references. Our evaluation reveals two failure modes: generative SR can synthesize misleading details, whereas restoration-oriented SR can leave critical evidence blurred or ambiguous. These findings motivate improving faithful detail recovery in restoration-oriented SR, where a key training challenge is to provide sufficiently difficult inputs while retaining recoverable visual information. We propose ReDiC (Recoverability-Difficulty Curriculum), which combines a model-independent recoverability proxy with model-relative restoration difficulty to adapt training degradation severity. ReDiC increases severity when inputs are recoverable and restoration is easy, maintains challenging but recoverable conditions, and reduces severity when estimated recoverability is low. It modifies only training degradation generation, leaving the SR architecture and reconstruction objective unchanged. Across NAFNet, SwinIR, and MambaIR, ReDiC improves average PSNR by approximately 2.5 dB and HR-referenced semantic scores by about 3 points over the corresponding baselines on synthetic benchmarks, with further gains confirmed by LLM-based and human evaluations on 200 real smart-glasses captures.

cs.CV

新论文 · v1arXiv:2611.23673

Communicative On-Policy Distillation: Distilling Black-Box Teacher Capabilities through Communication for Long-Horizon Tasks

Lirui Luo, Kelong Mao, Xinwei Yang, Rongqing Li, Luyu Chen, Kieran Wong, Yudong Guo, Xinrui Wang 等 12 位作者

原文摘要

On-policy distillation (OPD) is a powerful paradigm for improving language-model agents on long-horizon tasks, yet its conventional formulation relies on teacher logits that text-only black- box models do not expose. To address this limitation, we introduce Communicative On-Policy Distillation (COPD), which uses natural-language communication as a medium for distilling a stronger model's capabilities into a smaller student. During task execution, the student au- tonomously decides when to consult a black-box teacher and formulates open-ended natural- language requests without predefined question templates or intervention schedules. Successful student-teacher interactions are retained as privileged references to supervise fresh adviser-free student rollouts through on-policy self-distillation, jointly with task-reward reinforcement learning. On CAMG-II, COPD achieves 2.46 times the gain of the strongest black-box OPD baseline. The capabilities it learns through communication generalize to Terminal-Bench 2.1 and SWE-Bench Pro V2, improving task success without adviser access.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.23672

Image-Condition-Controlled Diffusion Network with Large-Scale CT Pretraining for CT-Free Attenuation Correction in Dynamic Cardiac PET

Zhejia Zhang, Scott M. Leonard, Jinkui Hao, Ryan J. Avery, Richard L. Weinberg, Bo Zhou

原文摘要

Positron emission tomography (PET) provides quantitative information on myocardial perfusion. In dynamic PET, tracer kinetics are tracked through a series of reconstructed time frames. Reliable attenuation correction is essential for accurate measurements. Clinical attenuation maps ($μ$-maps) are typically derived from computed tomography (CT), which adds radiation exposure and may introduce PET-CT misregistration due to respiratory and cardiac motion. Moreover, supervised CT-free methods rely on paired non-attenuation-corrected (NAC) PET and CT data, which are scarce, whereas large-scale unpaired CT data are more readily available. To address these challenges, we propose Large-scale Unpaired CT-Informed Diffusion (LUCID), a framework that transfers anatomical priors learned from 10,000 chest CT volumes in the public CT-RATE dataset to $μ$-map synthesis for dynamic cardiac $^{82}$Rb PET. First, a convolutional neural network (CNN) predicts an initial $μ$-map from each NAC PET frame. Second, the CT-pretrained diffusion backbone refines a low-noise perturbation of the CNN prediction through a single denoising step, conditioned on the corresponding NAC PET frame via ControlNet. Finally, frame-wise predictions are averaged voxel-wise to obtain the final $μ$-map. We further introduce the voxel-wise temporal standard deviation (TSD) to quantify inter-frame variability without requiring a reference $μ$-map. We evaluated LUCID on an in-house dataset of 102 patients and found that it achieved the best quantitative accuracy while maintaining competitive inter-frame consistency. Ablation studies showed that refinement with a diffusion backbone pretrained on in-house CT data from the training patients was less accurate than the CNN prediction alone, highlighting the importance of large-scale CT pretraining.

cs.CV

版本更新 · v4arXiv:2311.10959

Structure-Aware Sparse-View X-ray 3D Reconstruction

Yuanhao Cai, Jiahao Wang, Alan Yuille, Zongwei Zhou, Angtian Wang

原文摘要

X-ray, known for its ability to reveal internal structures of objects, is expected to provide richer information for 3D reconstruction than visible light. Yet, existing neural radiance fields (NeRF) algorithms overlook this important nature of X-ray, leading to their limitations in capturing structural contents of imaged objects. In this paper, we propose a framework, Structure-Aware X-ray Neural Radiodensity Fields (SAX-NeRF), for sparse-view X-ray 3D reconstruction. Firstly, we design a Line Segment-based Transformer (Lineformer) as the backbone of SAX-NeRF. Linefomer captures internal structures of objects in 3D space by modeling the dependencies within each line segment of an X-ray. Secondly, we present a Masked Local-Global (MLG) ray sampling strategy to extract contextual and geometric information in 2D projection. Plus, we collect a larger-scale dataset X3D covering wider X-ray applications. Experiments on X3D show that SAX-NeRF surpasses previous NeRF-based methods by 12.56 and 2.49 dB on novel view synthesis and CT reconstruction. Code, models, and data are released at https://github.com/caiyuanhao1998/SAX-NeRF . Our project page at https://caiyuanhao1998.github.io/project/SAX-NeRF/ shows more video and interactive results. An online Gradio demo is available on HuggingFace at https://huggingface.co/spaces/CaiYuanhao/SAX-NeRF

eess.IV · cs.CV

新论文 · v1arXiv:2611.23671

A Free Lunch: Gradient Averaging Achieves Optimal Statistical Efficiency in Newton Sketch

Haoxuan Wang, Jianliang Ye, Sen Na

原文摘要

We study statistical inference for online sketched Newton methods, in which each Newton system is approximately solved by an inner randomized sketching solver. Existing work reveals a computational--statistical trade-off: the sketching solver (and its accelerated variants) reduces the per-step cost of Newton methods from $O(d^3)$ to $O(d^2)$, but the randomness introduced by sketching also inflates the limiting covariance of both the last and the averaged Newton iterates. In this work, we address this trade-off via gradient averaging. We show that simply replacing the stochastic gradient with a moving average at each step can mitigate, and in some cases eliminate, the trade-off in Newton sketch. Importantly, gradient averaging requires no additional oracle evaluations and leaves the contraction bound of the inner sketching solver unchanged. In particular, we prove that the last sketched Newton iterate with gradient averaging attains a limiting covariance no larger than that without gradient averaging, while the averaged iterate even attains the minimax optimal limiting covariance, matching that of the exact Newton method. To our knowledge, this is the first analysis showing that randomness introduced to improve computational efficiency need not compromise statistical efficiency as long as proper gradient estimates are used. The key analytical challenge is that gradient averaging destroys the crucial martingale difference structure underlying central limit theorem arguments. We overcome this challenge by analyzing the coupled two-timescale recursions governing the iterate and the gradient estimator. Numerical experiments on linear and logistic regression support our theoretical covariance comparisons.

stat.ML · cs.LG · math.OC · stat.CO

新论文 · v1arXiv:2611.23670

EyeDiT: Anatomy-Grounded Multi-Modal Eye Generation and Simulation

Yonghan Lee, Zachary Willms, Kun Liu, Pushkar Anand, Ali Behrooz, Dmitri Model, Dinesh Manocha, Yatong An

原文摘要

Synthetic eye data are critical for rapid development of eye tracking (ET) in AR/VR applications. However, existing synthetic eye generators are largely image-centric and lack a high-quality underlying 3D anatomy of the eye, which limits their control mainly to the gaze and provides no anatomical labels. To address this problem, we propose EyeDiT, an anatomy-grounded, multi-modal 3D eye generation and simulation model trained with optical coherence tomography (OCT), labeled anatomy point clouds and near-eye images. Our pipeline first trains a Multi-Modal Anatomy Variational Autoencoder (VAE), which encodes an anatomy-aware latent representation from all input modalities. Then, our Eye Latent DiT is trained to generate latent samples conditioned on the optical axis, the pupil position and radius, and the subject identity. Together with Gaussian decoders for novel-view simulation, our model enables control over the pupil, subject identity and viewpoint for data synthesis. We show that our model outperforms previous eye image synthesis models in novel-view synthesis (24.9 against 21.8 dB PSNR from a single view), and that a public ET neural network trained on our synthetic data shows a smaller sim-to-real gap than when trained on data from other generators (3.5$^\circ$ vs. 8.4$^\circ$ gaze error), approaches a network trained on real data, and further improves ET performance when combined with real data (2.3$^\circ$ vs. 2.6$^\circ$). More information is available on the project page: https://lyhan12.github.io/eyedit

cs.CV

新论文 · v1arXiv:2611.23664

CratesBump: A Version-Bump Dataset for the Rust Ecosystem

Muhammad Hassnain

原文摘要

We release CratesBump, the first public dataset for predicting version bumps in the Rust ecosystem, together with semver-extract, the tool that builds it. CratesBump is built from every crate on crates.io with at least two releases before 14 September 2026 (about 220,000 crates), giving over two million consecutive release pairs. Each pair has 41 features (code changes from AST diffs, dependency changes, complexity, release cadence, GitHub commit and issue activity), its source repository where listed, and two labels: the literal reading of MAJOR.MINOR.PATCH, and Cargo's rule, under which a 0.y bump is a breaking change. semver-extract regenerates the dataset from public crates.io data and the GitHub API. To illustrate its use we (i) benchmark bump predictors on held-out repositories, finding the task learnable but far from solved, with lower scores on later releases; (ii) measure which feature groups carry the signal; (iii) check, against declared dependency ranges, how often Cargo's rule shields dependents from pre-1.0 breaking releases; and (iv) audit a sample of releases with cargo-semver-checks, finding minor and patch releases that break the public API despite their version number. Dataset and tool are released under open licenses.

cs.SE · cs.LG

版本更新 · v2arXiv:2611.00515

AStockArena: Beyond Returns, Can We Entrust Real Capital to the Decisions of Financial Agents?

Zeyu Liu, Sing Kwong Lai, Xuanzhi Feng, HaoYang Shang, Yang Li, Zihao Fang, Xuan Liu, Song Guo

原文摘要

Large language models (LLMs) are increasingly used in dynamic financial trading, yet real-time trading benchmarks mainly evaluate agents by cumulative returns and risk-adjusted performance. Such outcome metrics cannot show whether trades are faithfully reported, supported by available evidence, and consistent with account states. We introduce AStockArena, a real-time decision-auditing benchmark for continuous trading in China's A-share market. Under shared market conditions and execution constraints, we evaluate 13 open- and closed-source models over 3,198 sequential decisions. AStockArena reconstructsthe actions actually posted to accounts by aligning reports, trade requests, execution responses, and account states, and audits them with eight checks spanning execution traceability (O), evidence sufficiency (RK), and financial meta-awareness (B), combining record verification with consensus expert annotation. Of 1,070 trading points, 72.99% exhibit at least one audit gap; model-level rates range from52.2% to 91.2%, with evidence gaps most prevalent. Historical trade-filtering replay further shows thatportfolio outcomes are sensitive to these flagged trades. Decision-process auditing thus offers a verifiable complement to return-based evaluation of financial agents.

cs.CL · cs.AI

新论文 · v1arXiv:2611.23663

Lodestone: Automated Semantic Discovery of Datacenter Hardware Specialization

Peizhe Liu, Akanksha Jain, Gerasimos Gerogiannis, Vidushi Dadu, Parthasarathy Ranganathan, Jovan Stojkovic

原文摘要

Hardware specialization can improve datacenter efficiency. Unfortunately, identifying computations that justify dedicated hardware is difficult. Existing approaches analyze hot functions, instruction patterns, or overheads such as datacenter tax. They can miss fine-grained computations whose aggregate cost is spread across applications and libraries, especially when different pieces of code obscure the same underlying computation. We observe that seemingly unrelated code regions often perform the same computations, creating specialization opportunities that require semantic reasoning. The rise of agentic AI makes it possible to automate this. However, conventional AI agents cannot efficiently and reliably analyze large scale datacenter software. To unlock this opportunity, we present Lodestone, an agentic framework that automatically discovers hardware specialization opportunities by reasoning about what the executed code computes. First, Lodestone extracts hot control-flow regions from execution traces across workloads and organizes them into compact analysis packages that make large workloads tractable for agents. Second, agents describe what each region computes, merge those that perform the same computation into computational families, and check their semantic correctness in a loop. Third, to verify the discovered family, Lodestone runs every piece of code in a family against a set of reference inputs and outputs on recorded executions. Finally, for selected families, Lodestone proposes hardware, e.g., ISA extensions, near-core units, or detached accelerators, and human experts decide which proposals to develop further. We evaluate Lodestone on 20 workloads across six datacenter workload categories. We simulate 30 discovered families in a cycle-accurate simulator and implement them in RTL. These optimizations speed up the workloads by 12.6% on average and by up to 80.2%.

cs.AR · cs.AI

版本更新 · v2arXiv:2611.19802

Machine interpreting competitiveness: a discourse-sensitive comparison of meaning and target-language quality in English-Chinese simultaneous interpreting

Yuanyuan Ding

原文摘要

Machine interpreting (MI), or AI-enabled speech translation, is increasingly visible in professional and public-facing communication, yet its performance relative to human simultaneous interpreters remains insufficiently understood. Existing studies are often limited by a single discourse mode and evaluation frameworks that are not well aligned with interpreting as a discourse-level communicative activity. The present study compares five commercial MI systems with 26 human interpreters (14 professionals, 12 advanced students) on English-to-Chinese simultaneous interpreting across planned and unplanned discourse, focusing on meaning and target-language quality. In these materials, MI performance differed sharply between the two discourse modes. In the planned formal speech, the strongest system became highly competitive on meaning, entering the upper human range, and a second system also performed strongly. In the extemporaneous interview, however, no MI system approached the stronger human tiers. Code-level analysis further shows that similar overall scores often masked different error profiles. Human interpreters were more likely to preserve the broader communicative trajectory through selective omission, restructuring, and contextual inference, whereas even the best MI systems were more vulnerable to semantic distortion, discourse-tracking failures, and context-insensitive interpretation. On target-language quality, the human advantage proved more stable than on meaning. Unintelligible or nonsensical output and disfluency carryover emerge as particularly salient weaknesses in machine performance, especially in spontaneous discourse. Overall, the findings are consistent with a discourse-sensitive account of where MI appears competitive, where it remains limited, and why these distinctions matter for interpreting practice, interpreter education, and future MI development.

cs.CL

版本更新 · v3arXiv:2611.16301

Local Coordination for Efficient Small-Model RL on TPUs

Loki Chen, Gregory B. Rehm, Yang Song, Hongye Xie, Ming Lei, Chongyang Bai, Bob Kamma, Mingfu Liang 等 16 位作者

原文摘要

Reinforcement learning (RL) increasingly targets small language models, and executing these workloads efficiently across multiple accelerators requires effective coordination. On TPUs, Pathways-based RL uses a single controller to coordinate computation across hosts. This execution model is effective for large models, but its coordination computational costs are harder to amortize when small models repeatedly invoke short computations. To characterize these computational costs, we sweep dense models from 0.6B to 405B parameters on TPU v7x under a decode-heavy workload and measure how host and network computational overhead vary with model size. At 0.6B, host orchestration occupies 36% of step time and network communication 2%, whereas for large models, estimated network computational costs dominate the non-compute time. Motivated by these findings, we present Local Coordination JAX (LoCoJAX), which implements local rollout and reward processing on each TPU host with synchronous global training. In controlled comparisons against a tuned and optimized Pathways baseline on Qwen3-0.6B across three workloads and 8-64 TPU v7x chips, its colocated mode (LoCoJAX-CO) is 1.3-3.6x faster per step; on GSM8K, it completes a step faster on 8 chips than Pathways does on 64. Finally, a Ray-managed disaggregated mode (LoCoJAX-DA) overlaps rollout and training on separate hosts, and placement experiments establish when this overlap compensates for dividing devices and transferring weights: only when rollout dominates the step and receives most of the hosts. On NuminaMath-CoT at 256 chips, giving rollout 75% of hosts cuts step time by about 15% compared with LoCoJAX-CO.

cs.LG · cs.DC

版本更新 · v2arXiv:2606.26432

Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees

Yingshuo Wang, Xian Sun, Yanhang Li, Zhichao Fan, Zexin Zhuang

原文摘要

Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price can increase predicted demand, implied estimates of willingness to pay are frequently negative or implausible, and unavailable alternatives receive nonzero probability. We propose TabFM-Logit, an adapter that takes a foundation model's predicted choice probabilities as a precomputed feature and embeds them inside a multinomial logit's utility. In Stage 1, we fit the multinomial logit's structural coefficients by maximum likelihood with sign constraints. In Stage 2, we freeze those coefficients and fit a small neural correction operating on the foundation model's predictions. We prove that this composition exactly preserves the multinomial logit's marginal rate of substitution, so the analytically computable value of time becomes a mathematical guarantee rather than an empirical accident, and that training the two stages jointly breaks identifiability of the structural coefficients. Counterfactual derivatives and response signs are therefore the multinomial logit's by construction, and the foundation model contributes accuracy on observed choices. On respondents and households unseen in training, the adapter gains 5.7-6.8 percentage points (pp) of test accuracy on Swissmetro, 1.5 pp on LPMC, and 3.3-3.6 pp on IoT-Wearables over the multinomial logit (4.2 pp on average), stays within 1.0 pp of the raw foundation model, maintains 100% cost monotonicity, and keeps the multinomial logit's values of time exactly. The gain is largest where the multinomial logit is weakest and smallest where it is already strong. In every case it comes with the multinomial logit's guarantees, which the raw foundation models lack.

cs.LG · econ.EM

新论文 · v1arXiv:2611.23661

LightSEAD: Lightweight SE(3)-Aware Keypoint Detector through Selective Knowledge Distillation

Mayowa Adebambo, Alexander D. Rast, Andrew Bradley

原文摘要

The pursuit of improved performance in deep learning has often been accompanied by increasing architectural complexity and computational demands. We explore an alternative direction: achieving more with less through structured supervision. We introduce LightSEAD, a lightweight SE(3)-aware keypoint detector initialised with calibrated Harris pseudo-labels and enriched through viewpoint-aware and appearance-aware supervision and selective knowledge distillation. LightSEAD comprises only six convolutional layers and 84,289 learnable parameters, achieving competitive repeatability across HPatches, KITTI 06 and 4Seasons while demonstrating its downstream applicability to relative pose estimation on MegaDepth-1500. Further optimised for mixed-precision inference, LightSEAD Coarse achieves approximately 909 FPS on an NVIDIA RTX 4090 and 139 FPS on a Jetson Orin Nano Super.

cs.CV · cs.RO

版本更新 · v3arXiv:2607.13796

A Geometric Coding Theorem

Romie Banerjee

原文摘要

This paper establishes a direct analogue of the classical Coding Theorem in the setting of symmetry groups. We consider computable bijections on the set of binary strings and define the symmetry prior of a string x as the probability that a randomly chosen symmetry from a given group G has x as its unique fixed point. We show that for any fix-retractable symmetry group G, a group admitting a computable section that selects an isolating symmetry for every string, the symmetry prior is a universal lower semi-computable semi-measure. In this case, the Geometric Coding Theorem holds. This result is a coding-theoretic restatement of a theorem of Trejo, Kreinovich and Longpré, who showed that the complexity of describing a string by a symmetry with that string as its unique fixed point equals its Kolmogorov complexity. Our contribution is to recast it in terms of algorithmic probability and to treat the symmetry group as a parameter, identifying fix-retractability as exactly the condition under which symmetry complexity collapses onto Kolmogorov complexity.

cs.IT · cs.AI · math.CT · math.GR

新论文 · v1arXiv:2611.23657

Same Model, Different People: Numerical Execution Contracts and the Reproducibility of Fairness Audits

Erzheng Zhang, Agnes Chu

原文摘要

Fairness audits treat a trained model as a fixed decision function, but the arithmetic that evaluates it is part of that function. This study holds the model, records, threshold and audit code fixed and varies the numerical execution contract in two tiers. Tier 1 changes only how products and sums are computed, with the serialized weights byte-identical, and is the causal test of arithmetic. Tier 2 runs reduced-precision deployment configurations (BF16 compute, FP8 and 8-bit weights), which can also round weights and change engines and kernels, so its effects belong to the configuration. It audits three tabular model families and two open-weight language models (4B and 24B parameters) on four public tasks, including hospital readmission, on CPUs and GPUs from NVIDIA, AMD and Apple. Tier 1 changed decisions near the threshold, and which ones depended on the GPU and its software stack, but no verdict under the prespecified, unweighted tests. Tier 2 configurations changed more decisions and some diagnostic verdicts, but no four-fifths verdict. Serving the 24B model with vLLM FP8 selected 54% of people rather than 45% and passed an employment-status audit by sex that its strict FP32 reference failed: its demographic-parity and equalized-odds gaps fell from 0.0567 and 0.0515 to 0.0417 and 0.0394, against a diagnostic tolerance of 0.05. At the reference's selection count FP8 failed demographic parity, and no reading gave its equalized-odds change a paired interval excluding zero. The declared audit depends on the configuration; FP8 is not shown to be fairer. At the frozen thresholds, every pass-fail verdict a configuration changed had a sampling interval containing its criterion. It proposes an audit stability protocol in which the auditor declares contracts, groups, weights and tests before scoring and records each verdict's range over them apart from its sampling uncertainty.

cs.CY · cs.LG

新论文 · v1arXiv:2611.23654

Radar-Native Control Barrier Functions: Doppler Range Rate as a Measured Barrier Derivative

Johannes Mootz, Hesam Mojtahedi, Reza Akhavian

原文摘要

Safe control around dynamic obstacles requires information about both distance and relative motion. Range-based filters commonly reconstruct the required range rate from successive range measurements or from obstacle-state estimators, which can introduce estimator delay or sensitivity to range noise when obstacle motion changes. A frequency-modulated continuous-wave (FMCW) radar measures radial relative velocity directly through Doppler. We use this measurement as the derivative of an ego-centered range control barrier function (CBF) and obtain a closed-form filter on the robot's forward velocity. A measurement margin constructed from sensor error bounds accounts for errors in range, Doppler, ego velocity, and bearing. In 508 paired encounters within the platform's retreat capability, direct Doppler produces two buffer incursions, compared with 15 for a constant-acceleration and 25 for a constant-velocity Kalman filter. On a Unitree Go1, the controller stops at $0.777 \pm 0.015$ m against the predicted $0.758$ m and reacts to a farther approaching object while a nearer static return remains. The guarantee covers the longitudinal range channel under bounded measurement errors and continuously available detections. Direct Doppler removes the need to reconstruct range rate in the safety loop, reducing the delay between a change in obstacle motion and its effect on the safety command.

cs.RO · eess.SY

版本更新 · v2arXiv:2609.20441

Distilling a Geospatial Foundation Model into Compact Surface-Water Segmenters

Fabian Schmalstieg, Karsten Mueller, Wojciech Samek

原文摘要

Geospatial foundation models segment surface water accurately, but their size limits deployment on edge hardware. Therefore, we distill a 300-million-parameter Prithvi-EO-2.0 teacher, fine-tuned on the 252 hand-labeled Sen1Floods11 training images, into compact student models. The teacher labels 2,500 Sentinel-2 images around flood alerts and supervises the students via its labels and probability maps, without manual annotation. A 0.7-million-parameter EfficientViT-B0 student achieves the teacher's accuracy in water intersection over union (IoU) on WorldFloods-v2, STURM-Flood and 97 held-back WorldFloods events. Unlike prior work, we evaluate every model on four test sets from three public datasets and on two new dry-scene sets. Controlled comparisons show that teacher labels achieve human-level annotation quality for student training on the same images. The teacher's probability maps account for much of its value, and the full pipeline adds 5.7 IoU points on the held-back events over training on hand labels alone. All students, with parameter counts ranging from about 1,000 to 32.5 million, perform within 2 IoU points of the teacher on WorldFloods-v2 and STURM-Flood. On a Jetson Xavier NX, the main student runs as a 1.6-megabyte mixed 8-bit integer and 16-bit floating-point engine at 4.9 milliseconds per 512-by-512 image, and a 12,230-parameter student runs in full 8-bit integer format within 0.5 IoU points of its 32-bit version. The main student outperforms a fixed water index by 11.5 IoU points on the held-back events and raises false alarms on under 10\% rather than 57.0\% of water-free windows, as unattended use requires.

cs.CV · cs.LG

新论文 · v1arXiv:2611.23651

Safe Personal RSI: Evaluating and Repairing Personal-Agent Updates

Jiapeng Pei, Yuhang Yao, Sitan Liu, Hanxin Chen, Hao Li, Guogeng Li, Jiapei Liu, Ruijie Chen 等 12 位作者

原文摘要

Kicker is a personal health assistant. Changes to an assistant's reusable instructions can improve task handling while changing what it discloses, which requests it follows, and how it reports actions. We study Safe Personal RSI, an update-evaluation component developed for Kicker. We restrict recursive self-improvement (RSI) to prompt updates, with model weights and runtime code fixed. The procedure tests proposed and current instructions, repeats failing cases, temporarily undoes changes to guide repairs, and checks safety and task performance before adoption. If no version passes, the current instructions stay in use. Our executable benchmark contains 29 email, calendar, health, and marketplace cases, with separate probes for authorization reuse, memory, and tool-output injection. Across three models and two deliberately risky edits, the procedure rejects 20 of 21 update attempts. In repair confirmation, an admitted GPT-5.6 Luna repair reduces attack violations from 10.7% to 0% and increases safe task completion from 89.7% to 100%; a broad handwritten authority rule matches these outcomes. Under stronger attacks, a repair transferred from Qwen2.5-7B-Instruct to Qwen3-14B reduces violations from 69.0% to 17.9% and increases safe task completion from 19.5% to 64.4%. Separate runtime probes examine memory-entry deletion and identify missing local OAuth scope checks in the evaluated snapshot.

cs.SE · cs.AI · cs.CL

版本更新 · v3arXiv:2609.40290

Orbits as Strong Models: Kolmogorov Structure Function under Symmetry

Romie Banerjee

原文摘要

Strong models in algorithmic statistics are essentially the cells of simple partitions of $\{0,1\}^n$. We study the partitions that come from symmetry, the orbit partitions of groups acting on strings, and the structure function $h^G_x$ they induce. A set is a cell of such a partition exactly when its setwise stabiliser acts transitively on it, so $h^G_x$ is Kolmogorov's structure function restricted to $G$-homogeneous sets. For the full symmetric group this recovers all models and exactly the strong ones. For $GL(n,2)$ the cells are the linearly homogeneous sets, $h^{GL}_x$ lies in a band between $C(x)-α$ and $n-α$ with both edges attained, and some stochastic normal strings have simple structure that is invisible to linear symmetry. Writing each permutation group as a Burnside-ring type with a placement, we show that any space of symmetry hypotheses small enough to search is small enough to miss simple structure. Finally we cast the search for orbit models as value estimation on subgroup lattices, with computable bounds, certified training targets and a lattice version of Monte Carlo tree search.

cs.IT · cs.AI · math.GR

新论文 · v1arXiv:2611.23648

Toaster: Nonlinear Memory from Cascaded Linear Memories and Target Propagation

Zeman Li, Ali Behrouz, Yuan Deng, Praneeth Kacham, Rami Al-Rfou, Meisam Razaviyayn, Vahab Mirrokni

原文摘要

Recurrent memories let language models process long sequences with a fixed-size state. Linear memories such as DeltaNet and KDA store one matrix and take one delta-rule step per token. The product of a chunk of such steps has an exact WY form, so they train fast. Deep memories such as TTT-MLP and Titans store a small MLP, which can hold maps that no matrix can, but their update has no WY form. Toaster bridges the two by building on a known fact: a gradient step on a linear layer is a delta-rule write. It builds a two-layer nonlinear memory from two linear memories with an activation between them. We use target propagation to give the hidden memory its values by projecting the output error back through the second memory. Given a chunk's cross-layer signals, approximated once per chunk, each layer can then run on an unmodified delta-rule kernel. Our default runs this kernel on the output layer and updates the hidden layer once per chunk. Running it on both layers gives a better model in our ablation. At matched backbones and training-token budgets, Toaster has lower loss than KDA at all five tested sizes (0.2B-1.6B non-embedding parameters) on both C4 and PG19. Its C4 perplexity also matches or slightly improves on the attention baseline at every size. At 1.2B it is also below Titans. In a 3:1 hybrid with global attention, the Toaster hybrid has the lowest perplexity of the four hybrids tested, and it is 0.18 (C4) and 0.44 (PG19) below the attention baseline. At the largest size, Toaster's mean three-shot accuracy on 13 tasks is 51.84%, compared with 50.52% for KDA and 50.04% for Titans. In length extrapolation, Toaster's loss stays below KDA's up to 20K tokens (5x the training length). On the 145M backbone, at a hidden width matched to Titans' memory, Toaster takes at most 1.33x KDA's training-step time and is 2.8-5.5x faster than the tested Titans configurations at 32K context.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.02527

CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization

Jiaxuan Luo, Xingguo Xu, Shanshan Wang, Yuhan Zhou, Zhen Zhang

原文摘要

Learned visual reward models score a robot's execution from camera images and an instruction, and are increasingly used to fine-tune robot policies. Two checks decide whether to trust one: the reward model separates successes from failures, and task success rises during training. We show that both checks can pass while the policy learns to act on the wrong object. When a diffusion policy is fine-tuned against the reward model Robometer to open a drawer, task success rises by 10.2 percentage points. Wrong-object failures, which open a different drawer, rise by 10.9 points, whereas the same training on the simulator's task-completion signal raises success alone. A second reward model, RoboReward-8B, behaves the same way, and the effect reappears on a physical robot. This happens because of how the reward scores the policy's own failures. Most failures make little progress and score low, while a wrong-object failure looks like progress and scores well above them. Optimization shifts a policy toward outcomes that score above the executions they compete with, the executions they can take the place of. It therefore turns low-scoring failures into both successes and wrong-object failures, even when the reward model scores successes higher. This rule needs only executions of the initial policy, so it can be tested before training. On a stacking task we predicted which of three object placements Robometer would exploit, and training raised wrong-object stacks from 20% to 69% in that placement and in neither of the others. The same rule gives a check to run before optimization and a repair that needs no labels: scoring each execution again on frames re-rendered with the objects the instruction does not name put back removes the amplification on both tasks and on the robot.

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.23646

PRISM: Profiling and Representation of Individual Stereotypical Motion

Austin A. MBaye, Savik Kinger, Matthew S. Goodwin

原文摘要

An anatomical pose provides interpretable joint structure, but no fixed set of physical landmarks can fully specify a person's movement. We introduce PRISM, a complementary representation that characterizes repetitive movement using tracked masks and dense optical flow. Torso-relative flow measures intensity, frame-wise mask variation measures spatial extent, signed-flow recurrence estimates frequency, and persistent sliding-window geometry describes the rhythmicity of the movement. Across 1,890 synthetic conditions, the measurements recover controlled speed, amplitude, and frequency while exposing observation limits. An idealized hand-motion experiment demonstrates variation omitted by identical exact COCO-17 trajectories; controlled corruption experiments separately examine measurement sensitivity. Audits of two pose methods on the same data cohort and 36,930 external skeleton clips document incomplete observation and dependence on processing choices. In 1,404 annotated complex stereotypical motor movement bouts from six autistic participants, total flow converges with pose motion, while matched-coordinate examples and repeated-session profiles show differences in intensity, extent, frequency, and rhythmicity within behavior labels. A separate VLM comparison evaluates quantitative frequency estimation, and a profile-conditioned decoder links the measurements to illustrative skeletal movements. PRISM connects numerical profiles to visible examples, providing an interpretable way to compare how the same behavior is expressed beyond its label or event count.

cs.CV

版本更新 · v4arXiv:2305.10299

Binarized Spectral Compressive Imaging

Yuanhao Cai, Yuxin Zheng, Jing Lin, Xin Yuan, Yulun Zhang, Haoqian Wang

原文摘要

Existing deep learning models for hyperspectral image (HSI) reconstruction achieve good performance but require powerful hardwares with enormous memory and computational resources. Consequently, these methods can hardly be deployed on resource-limited mobile devices. In this paper, we propose a novel method, Binarized Spectral-Redistribution Network (BiSRNet), for efficient and practical HSI restoration from compressed measurement in snapshot compressive imaging (SCI) systems. Firstly, we redesign a compact and easy-to-deploy base model to be binarized. Then we present the basic unit, Binarized Spectral-Redistribution Convolution (BiSR-Conv). BiSR-Conv can adaptively redistribute the HSI representations before binarizing activation and uses a scalable hyperbolic tangent function to closer approximate the Sign function in backpropagation. Based on our BiSR-Conv, we customize four binarized convolutional modules to address the dimension mismatch and propagate full-precision information throughout the whole network. Finally, our BiSRNet is derived by using the proposed techniques to binarize the base model. Comprehensive quantitative and qualitative experiments manifest that our proposed BiSRNet outperforms state-of-the-art binarization methods and achieves comparable performance with full-precision algorithms. Code and models are publicly available at https://github.com/caiyuanhao1998/BiSCI and https://github.com/caiyuanhao1998/MST . An online Gradio demo is available on Hugging Face at https://huggingface.co/spaces/CaiYuanhao/MST

cs.CV · eess.IV

新论文 · v1arXiv:2611.23639

Searching the Pareto Front: Multi-Objective Retrieval for Heterogeneous Scientific Modalities

Song Young Oh, Nesar Ramachandra, Bin Xia, Ian Foster, Kyle Chard

原文摘要

In cosmology, surveys span different sky regions and wavelength ranges, resulting in uneven modality coverage across observational datasets. Such heterogeneity can be addressed through either multimodal foundation models (FMs), which learn shared embedding spaces, or independently learned modality embeddings combined via late fusion. We investigate whether the latter provides an adaptive alternative to FM-based scientific retrieval. We evaluate this approach on a galaxy retrieval task spanning diverse modalities--history of star formation, spectra of light emitted, and multi-wavelength observations from two telescopes--comparing an FM baseline with separately trained embeddings fused through multi-objective optimization based on Pareto optimality. We find that the FM baseline achieves strong embedding-space proximity, but our method preserves modality-specific distance structure that allows scientists to inspect which physical signals drive similarity. Our method also achieves improved fidelity in raw-data space: across six measured properties, its nearest neighbor is 8% closer to the query on average than that retrieved by kNN in the FM embedding space (spread 0.128 vs. 0.139). These results suggest that multi-objective retrieval can surface astrophysically coherent candidates that single-objective search alone may overlook.

cs.AI · astro-ph.IM

新论文 · v1arXiv:2611.23638

When Do LLMs Model the Right Target? Problem Formulation in High-Stakes Risk Prediction

Jennifer Zhang, Amanda Coston

原文摘要

Generative AI is increasingly used to assist with data science tasks, yet fundamental questions remain about its ability to correctly formulate analytical problems. We investigate how well large language models (LLMs) can formulate prediction problems when developing models for high-stakes decision making. We focus on one particular challenge to validity: decision dependency, which arises when historical decisions affect observed outcomes. We evaluate this aspect of problem formulation in LLM-generated code and explanations across child-welfare, healthcare, and employment settings, using 11 models from OpenAI and Anthropic and seven prompt conditions. We assess whether the LLM-generated code implements a procedure appropriate for estimating the intended outcome under the study's assumptions and whether the explanation acknowledges decision dependency. We find that LLMs do not reliably address decision dependency without guidance in the prompt. When prompts specify the target, the assumption needed to estimate it, and the estimation procedure, target-aligned implementation reaches 99-100%. Among frontier models, a simple prompt description of how decisions affect outcomes appears sufficient to elicit target-aligned implementation. Some responses also acknowledge decision dependency without addressing it in their code. Our findings suggest that analysts should not rely on LLMs to correctly formulate prediction problems without explicit methodological guidance and careful review. We propose validity-centered guidelines for LLM-assisted predictive modeling, covering prompt formulation, validation of the target and estimation procedure, and identification of key assumptions. Establishing validity is a necessary early step in evaluating whether to deploy a predictive model in a high-stakes setting, but deployment requires weighing broader ethical, institutional, and practical considerations.

cs.CY · cs.LG · stat.ME

版本更新 · v6arXiv:2411.14384

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

Yuanhao Cai, He Zhang, Kai Zhang, Yixun Liang, Mengwei Ren, Fujun Luan, Qing Liu, Soo Ye Kim 等 15 位作者

原文摘要

Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric cases. In this paper, we propose a novel single-stage 3D diffusion model, DiffusionGS, for object generation and scene reconstruction from a single view. DiffusionGS directly outputs 3D Gaussian point clouds at each timestep to enforce view consistency and allow the model to generate robustly given prompt views of any directions, beyond object-centric inputs. Plus, to improve the capability and generality of DiffusionGS, we scale up 3D training data by developing a scene-object mixed training strategy. Experiments show that DiffusionGS yields improvements of 2.20 dB/23.25 and 1.34 dB/19.16 in PSNR/FID for objects and scenes than the state-of-the-art methods, without depth estimator. Plus, our method enjoys over 5$\times$ faster speed ($\sim$6s on an A100 GPU). Our Project page at https://caiyuanhao1998.github.io/project/DiffusionGS/ shows the video and interactive results. The code and models are publicly available at https://github.com/caiyuanhao1998/Open-DiffusionGS . An online Gradio demo with high-quality mesh exportation is available at https://huggingface.co/spaces/CaiYuanhao/DiffusionGS-Object

cs.CV · cs.GR

首次观测 · 记录 #1软件学报:jos:7749软件学报

面向大语言模型智能体安全的异常检测方法综述

面向大语言模型智能体安全的异常检测方法综述

马云聪, 宋泓憬, 黄辰林, 于丰源, 程华, 丁滟, 杨任宇, 李爱平 等 9 位作者

AI 速读 基于摘要

该综述从模型层、认知层和交互层梳理LLM智能体安全威胁,提出基于双层复合图的异常检测方法分类,并构建多维度评估指标。

cs.* · cs.CL · cs.AI · cs.MA

软件学报 · 2026 · 正式发表

查看原文摘要

以大语言模型(large language model, LLM)为核心的智能体和多智能体系统, 凭借其卓越的意图理解、推理规划和执行能力, 正广泛应用于各个领域. 近年来, 随着LLM能力的提升及其与外部环境交互的加强, 针对智能体系统的攻击行为持续演化, LLM幻觉也难以避免, 导致智能体系统在实际应用中面临各种安全威胁. 现有研究表明, 仅依赖LLM自身的安全机制难以保证系统的安全性, 准确识别各种异常行为对于智能体生态的良性发展有重要意义. 围绕智能体安全的异常检测问题, 首先从模型层、认知层和交互层梳理了当前智能体系统面临的安全威胁; 其次, 从拓扑图视角对智能体和多智能体系统进行形式化表示, 提出基于双层复合图的分类方法, 对LLM智能体安全的异常检测方法进行综述和分析; 接着, 提出提升智能体可信度的6大安全目标, 并基于此构建一个多维度的异常检测评估指标, 且在主流模型下验证其有效性和鲁棒性; 最后, 讨论现有检测机制的主要挑战和未来发展方向.

新论文 · v1arXiv:2611.23633

Option-GRPO: Hierarchical RL Against AI Slop in Code Generation for Unseen SDKs

Prashank Kadam

原文摘要

Large language models increasingly produce AI slop in generated code: verbose, redundant, non-idiomatic implementations that pass functional checks but bloat codebases. The problem compounds on SDKs released after the model's training cutoff, where the model has neither idiomatic priors nor compositional understanding. We present Option-GRPO, a hierarchical reinforcement learning framework that adapts a code LLM to an unseen SDK from its source code alone, without human-written usage examples or test cases, and that explicitly optimizes for both functional correctness and code elegance. Our key insight is that SDK source code contains compositional structure that defines a hierarchy of reusable code patterns (code options) which simultaneously serve as the building blocks of a curriculum and the action space for efficient policy optimization. We show that code options induce a valid semi-Markov decision process, give conditional bounds under which shorter option description length implies more concise and, in expectation, more API-efficient programs, and analyze under stated assumptions how the option hierarchy improves credit assignment by a factor of $\sqrt{T/K}$. Using Group Relative Policy Optimization (GRPO) with execution-based rewards at each curriculum level, Option-GRPO discovers SDK idioms, composes them into patterns, and assembles patterns into complete programs. Experiments on 12 unseen SDKs with a 32B-parameter base model demonstrate 61.4% pass@1, outperforming flat GRPO by 8.7 points, ExploraCoder by 11.2 points, and ReCode by 6.3 points. Option-GRPO produces solutions that use 34.7% fewer API calls and are 27% shorter than flat-GRPO outputs while maintaining higher correctness, directly attacking the slop problem.

cs.SE · cs.CL · cs.LG